DIY GPU Machines

2026 NVIDIA GPU Quick Search Tool (Updated Sep 25, 2026)

Qualiteg Product Development Team

Apr 20, 2026 — 19 min read

We have made the full list of NVIDIA GPUs, past and present as of 2026, easy to filter. We hope it comes in handy when selecting a GPU!

The September 25, 2026 update separates Rubin (SM_107), the Blackwell 12.1 part (GB10 / DGX Spark) and the Ampere 8.0 parts (A100 / A30) into their own series. The previous edition is the 2025 NVIDIA GPU Quick Search Tool. For how to read the numbers see "Blackwell" Was Never One Compute Capability, and for the PyTorch side see PyTorch Versions and Supported NVIDIA GPU Compute Capability Levels.

NVIDIA GPU List Search

NVIDIA GPU List Search

Series	Category	Product Name	CUDA Cores	vRAM	Release Year	PCIe Version	Cooling	Power
Loading...

・ "Blackwell" Was Never One Compute Capability. Making Sense of NVIDIA's Compute Capability Numbers

Read more

Building a Coding Agent from Scratch, Part 2: The Completion Gate and What to Write in a Pushback

Building a Coding Agent from Scratch, Part 2: "Done" Means "It Runs," Not "It's Written." The Completion Gate and What to Write in a Pushback

The model's "Done" slipped through in five ways, from a bare syntax check to tests with no assert. We describe, with numbers, a completion gate that closes in three stages, and why a pushback should contain the failing lines and how to investigate, but never the answer.

Jev は入力を受け取り、型のついた判断を返す

Jev by TypeSafe AI: What It Is and How Well It Works, Measured Over 301 API Calls

Jev returns typed decisions instead of text. Signups reopened on September 28 with no free credit for direct accounts. We put $10 in, called it 301 times from Python, and measured accuracy on Japanese tickets, guardrails and command approval, plus response time and cost (about one yen).

"Blackwell" Was Never One Compute Capability. Making Sense of NVIDIA's Compute Capability Numbers

"Blackwell" Was Never One Compute Capability. Making Sense of NVIDIA's Compute Capability Numbers

Hello! If you work with NVIDIA GPUs, you run into numbers like sm_120 and sm_100 all the time. They are called Compute Capability numbers. They look like they map onto the product generation names. They do not. What sent us digging was TensorRT-LLM v1.3.0rc28, released on

Claude Opus 5.5 Complete Guide: Model Specifications, API Notes, and Claude Code Operations

Claude Opus 5.5 Complete Guide: Model Specifications, API Notes, and Claude Code Operations

A complete guide to Claude Opus 5.5: prices 20% below Opus 5 with 60% cheaper cache reads, API migration notes such as the medium default effort and thinking that can no longer be disabled, and the new default model and Fast mode in Claude Code.